Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.
Free
12 MCP servers
AI & AgentsWorks with ZedBy RudrenduPaul
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Free
Wraps the toolgovern CLI as a single generic MCP tool for agent-tool policy validation.
Free
Traces which neurons and attention heads drive a language model's output via MCP tools.
Free
Wraps the slop-eval CLI as a single generic MCP tool for genericness scoring of AI UI output.
Free
Verifies token/cost savings claimed by AI context-reduction proxies via MCP tools.
Free
AI agent observability with deterministic record/replay for debugging agent failures.
Free
Evaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.
Free
Fail-closed deterministic checks and hash-chained receipts for AI agent outputs via MCP.
Free
Benchmarks local LLM inference speed (tokens/sec) on your own hardware via MCP tools.
Free
Wraps the taskswarm CLI as a single generic MCP tool for multi-agent task coordination.
Free
Multi-agent context sharing, memory, and status coordination via MCP tools.
Free